qicesun/SRE-Agent-App
An Autonomous AI SRE Agent for Kubernetes, built with Java Spring Boot & LangChain4j. Implements OODA loop for self-healing.
This project offers an autonomous AI Site Reliability Engineer (SRE) to manage your Kubernetes clusters. It takes real-time cluster logs and status, analyzes them, and automatically performs tasks like restarting services or creating Jira tickets for complex issues. It's designed for DevOps engineers and SREs to reduce manual incident response.
Use this if you manage Kubernetes clusters and want to automate the detection, diagnosis, and resolution of common production incidents to reduce manual firefighting.
Not ideal if your organization doesn't use Kubernetes, GitLab, or Jira, or if you prefer a human-in-the-loop for all operational decisions.
Stars
64
Forks
—
Language
Java
License
MIT
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/qicesun/SRE-Agent-App"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Arvo-AI/aurora
Aurora — Open source AI-powered agentic incident management & root cause analysis for SREs....
a2wio/lucas
A2W's SRE agent for Kubernetes
datolabs-io/opsy
Opsy - Your AI-Powered SRE Colleague
scitix/siclaw
AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security...
pavangudiwada/awesome-ai-sre
AI SRE tools for RCA, Incident Response, Cost-Saving, Infra management, DevOps and more